Dash Version 4.0

Tempo Analysis

Histogram for tempo class corpus

From the histogram, we can see that the most frequent tempo (mode) in the class corpus is 85 BPM, with a count of 16.

85 BPM is relatively slow and could correspond to genres like hip-hop, downtempo electronic, or ballads.It also corresponds with the human heartbeat, which could explain a natural preference. The data displays several smaller peaks, this could hint at clusters of similar music.

Chordograms for own songs

Track 1: The first track, which is the ambient track, appears pretty uniform, smooth and continuous until the second minute, where it gets progressively broken up. This could be due to some subtle changes in the sound layers, while the song lacks a strong beat (as is often the case for ambient music).

Track 2: The second track, which is the breakbeat track, displays multiple evenly spaced lines. There is little variation visible aside from a small bridge, as the track mostly has a repetitive beat.

Chordogram -

Chromagram

Chromagrams for own tracks

!!! I currently keep having issues with my chromagrams not loading (though they do show in R), so it may be that they don’t show up yet. Trying to fix this ASAP.

Chromagrams capture the harmonic content by showing how energy is distributed across the 12 pitch classes over time.

This took quite a lot of time to display this graphic, you may set 'fastdisp=TRUE' for a faster, but less accurate, display
  • Evan-l-1.wav - Ambient
    • The energy is mainly in the lower frequency range, below ~5 kHz
    • The overall amplitude is low, this reflects the quiet ambient sounds
    • The minimal structure suggests an ambient or instrumental track
  • Evan-l-2.wav - Breakbeat
    • Covers a much wider frequency range, reaching beyond 10 kHz, with distinct variations in energy
    • Brighter colors indicate stronger amplitude, due to the track being comparatively dynamic
    • The structure implies prominent rhythmic and melodic elements, as is the case with my breakbeat track

SSMs

  • Evan-l-1.wav - Ambient
    • The chroma-SSM shows some variation, but overall pretty uniform and repetitive
    • The timbre-SSM is mostly smooth and table
  • Evan-l-2.wav - Breakbeat
    • The chroma-SSM has more distinct patterns, like a checkerboard. The song has stronger harmonic changes with varied chord progressions.
    • The timbre-SSM shows greater shifts in instruments or timbres

AI-Generated Tracks

These tracks were created using Stableaudio AI (Stableaudio). I took inspiration from genre tags on RateYourMusic and carefully crafted prompts using detailed descriptors to shape the sound. After generating the tracks, I simply downloaded the MP3 files.

Track 1: Meditative Ambient Soundscape

Style: Ambient, Post-Rock, Cinematic
Length: 2 minutes
Goal: A calm, meditative ambient with minimal instrumentation.

Tags Used:
Ambient, Post-Rock, Cinematic, Ethereal, Soothing, Meditative, Minimalist, Warm Subtle Bass, Deep Drones, Airy Pads, Textures, Analog Synths, Field Recordings, Wind Sounds, Reverb, 60 BPM —

Track 2: Energetic Breakbeat Rave

Style: Breakbeat, Acid Breaks, 90s Rave
Length: 2 minutes
Goal: A high-energy, chaotic breakbeat track.

Tags Used:
Breakbeat, Acid Breaks, 90s Rave, Energetic, Raw, Funky, Chaotic, Breakbeats, Deep Bass, Distorted 808, Acid Bass, Filtered Chords, Reversed Pads, Vocal Chops, 135 BPM

Track Creation

  1. Prompt Design:
    • Used RateYourMusic to explore fitting genre tags.
    • Structured prompts with specific instruments, moods, and BPM to guide the AI.
  2. Generation:
    • Entered prompts into Stableaudio AI.
    • Experimented with variations before selecting the best versions.
  3. Finalization:
    • Downloaded the MP3 files and ensured they matched my vision. =

Visualization

Here’s a scatterplot of the Danceability compared to the Tempo of the tracks. My track 1 (ambient) is marked red, track 2 (breakbeat) is blue.

Final Thoughts

There appears to be no set correlation between the danceability and tempo of the tracks. However, an interesting pattern emerges: there are two clusters—one with low danceability, and another with high danceability, while the tempo does not differ much.

Regarding my own tracks:

One particularly surprising observation is how the AI interpreted the second song’s tempo. While I set it to 135 BPM, it was classified as 93 BPM. This suggests that the AI might have emphasized a different rhythmic structure or half-time feel in its classification.